Dual-Foundation Models for Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2605.03365v1
• Date: Tue, 05 May 2026 04:52:08 GMT
• Title: Dual-Foundation Models for Unsupervised Domain Adaptation
• Abstract summary: Training segmentation models requires costly, labor-intensive annotations on real-world datasets.<n>Unsupervised Domain Adaptation (UDA) addresses this by training models on labeled synthetic data and adapting them to unlabeled real images.<n>We propose a dual-foundation UDA framework that leverages two complementary foundation models.
• Score: 2.279449016085348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets. Unsupervised Domain Adaptation (UDA) addresses this by training models on labeled synthetic data and adapting them to unlabeled real images. While conceptually simple, adaptation is challenging due to the domain gap, i.e., differences in visual appearance and scene structure between synthetic and real data. Prior approaches bridge this gap through pixel-level mixing or feature-level contrastive learning. Yet, these techniques suffer from two major limitations: (1) reliance on high-confidence pseudo-labels restricts learning to a subset of the target domain, and (2) prototype-based contrastive methods initialize class prototypes from source-trained models, yielding biased and unstable anchors during adaptation. To address these issues, we propose a dual-foundation UDA framework that leverages two complementary foundation models. First, we employ the Segment Anything Model (SAM) with superpixel-guided prompting to enable learning from a broader range of target pixels beyond high-confidence predictions. Second, we incorporate DINOv3 to construct stable, domain-invariant class prototypes through its robust representation learning. Our method achieves consistent improvements of +1.3% and +1.4% mIoU over strong UDA baselines on GTA-to-Cityscapes and SYNTHIA-to-Cityscapes, respectively.

Related papers

• CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation [19.197208667890337]
  We propose CVKD-UDA, which revisits voxel size as a core design factor to construct domain-similar representations.<n>We generate two complementary views by varying voxel sizes and introduce a cross-view knowledge distillation.<n>Experiments on two benchmarks demonstrate that CVKD-UDA effectively improves the performance of self-training methods.
  arXiv  Detail & Related papers  (2026-07-11T02:55:02Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning [34.786268652516355]
  Unsupervised domain adaptive segmentation aims to improve the segmentation accuracy of models on target domains without relying on labeled data from those domains. It seeks to align the feature representations of the source domain (where labeled data is available) and the target domain (where only unlabeled data is present)
  arXiv  Detail & Related papers  (2024-07-24T08:53:29Z)
• Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation [210.46684938698485]
  We study unsupervised domain adaptation (UDA) for semantic segmentation. We find that, by decreasing/increasing the proportion of training samples from the target domain, the 'learning ability' is strengthened/weakened. We propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy.
  arXiv  Detail & Related papers  (2023-03-16T05:04:10Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
  In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level. Our method produces state-of-the-art results on the C-Driving dataset.
  arXiv  Detail & Related papers  (2021-06-07T08:38:41Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)
• Adversarial Bipartite Graph Learning for Video Domain Adaptation [50.68420708387015]
  Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area. Recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations are not highly effective on the videos. This paper proposes an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions.
  arXiv  Detail & Related papers  (2020-07-31T03:48:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.